# bedrock

Amazon Bedrock is a platform for building generative AI applications and agents at production scale.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## A2A in Java: hands on Embabel

DevFeed: [A2A in Java: hands on Embabel](<https://devfeed.tech/articles/a2a-in-java-hands-on-embabel-22587.md>)

Original publisher: [Read original article](<https://medium.com/amex-gbt-technology/a2a-in-java-hands-on-embabel-b18d514be424?source=rss----60a0578f4096---4>)

Author: Aneshka Goyal

Published: 2026-06-21T07:01:03Z

Content type: tutorial

Language: en

Sources: [Amex GBT Technology](<https://devfeed.tech/sources/amex-gbt-technology.md>)

Topics: [Embabel](<https://devfeed.tech/topics/embabel.md>), [A2A protocol](<https://devfeed.tech/topics/a2a-protocol.md>), [Java](<https://devfeed.tech/topics/java.md>), [MCP](<https://devfeed.tech/topics/mcp.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Maven](<https://devfeed.tech/topics/maven.md>), [bedrock](<https://devfeed.tech/topics/bedrock.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [a2a](<https://devfeed.tech/tags/a2a.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [embabel](<https://devfeed.tech/tags/embabel.md>), [java](<https://devfeed.tech/tags/java.md>), [maven](<https://devfeed.tech/tags/maven.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>)

### AI overview

A hands-on tutorial for building a Java agent with Embabel. It demonstrates LLM-based story generation and review, Amazon Bedrock integration, a local Spring AI MCP server for word counts, Maven dependency management, and A2A-compliant endpoints.

### Source excerpt

Part 2: Hands on with Embabel! In Part 1, we discussed how Embabel works internally. In Part 2, we'll now try to get an application started that has an LLM interaction, talks to local MCP server (for tools), and helps us achieve a goal. This time, we'll also make sure we use A2A protocol for our agent (something Embabel makes easier to do allowing us to focus on core business logic and offloading boilerplate code to Embabel). We'll use the project creator to create a skeleton project for us with some Embabel dependencies and code. uvx --from git+https://github.com/embabel/project-creator.git project-creator Please note we can use Java or Kotlin as our preferred language, I would be leveraging Java. This is a simple story teller agent who writes a story and gets it reviewed (both story generation and review comes from LLM). We'd be using Bedrock for connection to our LLM model. For fetching the word count for a topic, it uses an MCP server which is a Spring AI MCP server running locally. Dependency management is handled using Maven, and the POM file looks like this: <?xml version="1.0" encoding="UTF-8"?> <project xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://maven.apache.org/POM/4.0.0" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd"> <modelVersion>4.0.0</modelVersion> <parent> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-parent</artifactId> <version>3.5.9</version> <relativePath/> <!-- Lookup parent from repository --> </parent> <groupId>com.example.demo-city-agent</groupId> <artifactId>Demo-city-agent</artifactId> <version>0.1.0-SNAPSHOT</version> <packaging>jar</packaging> <name>My first agent</name> <description>Generated agent project</description> <properties> <java.version>21</java.version> <embabel-agent.version>0.3.1</embabel-agent.version> </properties> <dependencies> <!-- Main Dependencies --> <dependency> <groupId>com.embabel.agent</groupId> <artifactId

## OpenAI and Amazon announce strategic partnership

DevFeed: [OpenAI and Amazon announce strategic partnership](<https://devfeed.tech/articles/openai-and-amazon-announce-strategic-partnership-6294.md>)

Original publisher: [Read original article](<https://openai.com/index/amazon-partnership>)

Published: 2026-02-27T05:30:00Z

Content type: news

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [amazon](<https://devfeed.tech/topics/amazon.md>), [Amazon Web Services (AWS)](<https://devfeed.tech/topics/amazon-web-services-aws.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [bedrock](<https://devfeed.tech/topics/bedrock.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-web-services-aws](<https://devfeed.tech/tags/amazon-web-services-aws.md>), [company](<https://devfeed.tech/tags/company.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [openai](<https://devfeed.tech/tags/openai.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

OpenAI and Amazon announce a multi-year strategic partnership involving AWS distribution of OpenAI Frontier, a Stateful Runtime Environment on Amazon Bedrock, customized models, AI infrastructure, and a $50 billion Amazon investment in OpenAI.

### Source excerpt

OpenAI and Amazon announce a strategic partnership bringing OpenAI's Frontier platform to AWS, expanding AI infrastructure, custom models, and enterprise AI agents.

## From Beta to Bedrock: Build Products that Stick.

DevFeed: [From Beta to Bedrock: Build Products that Stick.](<https://devfeed.tech/articles/from-beta-to-bedrock-build-products-that-stick-4299.md>)

Original publisher: [Read original article](<https://alistapart.com/article/from-beta-to-bedrock-build-products-that-stick/>)

Author: by Liam Nugent

Published: 2025-04-23T18:04:31Z

Content type: article

Language: en

Sources: [A List Apart: The Full Feed](<https://devfeed.tech/sources/a-list-apart-the-full-feed.md>)

Topics: [bedrock](<https://devfeed.tech/topics/bedrock.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [bedrock](<https://devfeed.tech/tags/bedrock.md>), [business](<https://devfeed.tech/tags/business.md>), [business-industry-usability-user-experience-user-research-web-strategy](<https://devfeed.tech/tags/business-industry-usability-user-experience-user-research-web-strategy.md>), [development](<https://devfeed.tech/tags/development.md>), [finance](<https://devfeed.tech/tags/finance.md>), [industry](<https://devfeed.tech/tags/industry.md>), [security](<https://devfeed.tech/tags/security.md>), [usability](<https://devfeed.tech/tags/usability.md>), [user-experience](<https://devfeed.tech/tags/user-experience.md>), [user-research](<https://devfeed.tech/tags/user-research.md>), [web-strategy](<https://devfeed.tech/tags/web-strategy.md>)

### AI overview

The article argues that financial products should be built around a stable bedrock of clear customer value rather than an accumulation of features. It discusses the risks of feature-first development, the role of a Minimum Viable Product, and the need to resist internal pressures that can produce confusing, bloated experiences.

### Source excerpt

As a product builder over too many years to mention, I've lost count of the number of times I've seen promising ideas go from zero to hero in a few weeks, only to fizzle out within months. Financial products, which is the field I work in, are no exception. With people's real hard-earned money on the line, user expectations running high, and a crowded market, it's tempting to throw as many features at the wall as possible and hope something sticks. But this approach is a recipe for disaster. Here's why: The pitfalls of feature-first development When you start building a financial product from the ground up, or are migrating existing customer journeys from paper or telephony channels onto online banking or mobile apps, it's easy to get caught up in the excitement of creating new features. You might think, "If I can just add one more thing that solves this particular user problem, they'll love me!" But what happens when you inevitably hit a roadblock because the narcs (your security team!) don't like it? When a hard-fought feature isn't as popular as you thought, or it breaks due to unforeseen complexity? This is where the concept of Minimum Viable Product (MVP) comes in. Jason Fried's book Getting Real and his podcast Rework often touch on this idea, even if he doesn't always call it that. An MVP is a product that provides just enough value to your users to keep them engaged, but not so much that it becomes overwhelming or difficult to maintain. It sounds like an easy concept but it requires a razor sharp eye, a ruthless edge and having the courage to stick by your opinion because it is easy to be seduced by "the Columbo Effect"... when there's always "just one more thing..." that someone wants to add. The problem with most finance apps, however, is that they often become a reflection of the internal politics of the business rather than an experience solely designed around the customer. This means that the focus is on delivering as many features and functionalities as pos

## Mistral: Are LLMs Commodities Now?

DevFeed: [Mistral: Are LLMs Commodities Now?](<https://devfeed.tech/articles/mistral-are-llms-commodities-now-33433.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2024/07/24/mistral>)

Published: 2024-07-24T09:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [LLMs](<https://devfeed.tech/topics/llms.md>), [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Google](<https://devfeed.tech/topics/google.md>), [bedrock](<https://devfeed.tech/topics/bedrock.md>), [groq](<https://devfeed.tech/topics/groq.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Latency](<https://devfeed.tech/topics/latency.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-strategy](<https://devfeed.tech/tags/ai-strategy.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [availability](<https://devfeed.tech/tags/availability.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data](<https://devfeed.tech/tags/data.md>), [google](<https://devfeed.tech/tags/google.md>), [google-cloud](<https://devfeed.tech/tags/google-cloud.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [groq](<https://devfeed.tech/tags/groq.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mistral](<https://devfeed.tech/tags/mistral.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>)

### AI overview

This opinion argues that the growing number of capable frontier language models, including Mistral 2 Large, GPT-4o, Llama 3.1, and Claude Sonnet 3.5, makes model selection increasingly resemble a commodity decision. It recommends evaluating cost, availability, and operator trustworthiness, and favors infrastructure providers that do not also train models.

### Source excerpt

Mistral 2 Large is out, and it's right up there with GPT-4o, ...and Llama 3.1, and Claude Sonnet 3.5, and...yeah, there's a lot of them. These "Frontier Models" are starting to look more like commodities. And with that shift, we need to adjust AI strategy to match. There's strong arguments to make for using an operator that doesn't also train models. Read more!